Beam 1.0 501B-A23B vs Sage-A1.5
Change modelsBeam 1.0 501B-A23BReflection AI
Sage-A1.5InternScience
IndexAll categories, out of 100.
60.2 ±4.6
60.5 ±9.4 best
GapIndex points below the top.
−0.3 · no clear gap
Top
CoverageIndex weight that has results.
85% best
60%
SpeedOutput tokens per second.
345/s
—
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
2026-10
2026-10
Input / 1MUS dollars per 1M input tokens.
—
—
Output / 1MUS dollars per 1M output tokens.
—
—
1K chats2K tokens in, 500 out, each.
—
—
1K documents20K tokens in, 1K out, each.
—
—
1K agent tasks200K tokens in, 20K out, each.
—
—
ContextMaximum tokens in one request.
1M best
262K
AgenticMulti-step tasks with tools.
59.3
59.4 best
CodingCode writing and repair.
62.0 best
57.3
ReasoningLogic problems and puzzles.
63.2
69.2 best
MultimodalTasks with images and text.
—
—
KnowledgeFacts and expert knowledge.
56.5
—
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
63.4
65.3 best
MathMath problems.
55.6
—
Benchmarks
7 sharedOnly Beam 1.0 501B-A23B: 23Only Sage-A1.5: 5
Beam 1.0 501B-A23B
Sage-A1.5